Borrowing it
Nothing to install: this file belongs to Weaverse/pilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Weaverse/pilot/main/AGENTS.mdgit clone --depth 1 https://github.com/Weaverse/pilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/weaverse/pilot/agents-md)<a href="https://agentmods.dev/instructions/weaverse/pilot/agents-md"><img src="https://agentmods.dev/badge/instructions/weaverse/pilot/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/weaverse/pilot/agents-md"><img src="https://agentmods.dev/badge/instructions/weaverse/pilot/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.04846 | $0.04846 |
| Opus 5.5 | $0.01938 | $0.01938 |
| Sonnet 5.5 | $0.00969 | $0.00969 |
| Haiku 4.5 | $0.00485 | $0.00485 |
Grade A, and why
pilot AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI agents (Claude, GitHub Copilot, Cursor, etc.) when working with code in this repository.
Canonical agent instructions:
AGENTS.mdis the source of truth and may always be updated. RootCLAUDE.mdis a relative symlink to it and must never become a separate copy. Push completed instruction changes to the repository's default branch.
Spec Maintenance
Required SDD convention: Every agent MUST read and follow
.claude/rules/spec-driven-development.md, the canonical companion rule. Summary only:
- Issue-first, single-spec: issues own owner/priority/milestone/status/discussion; one spec file owns requirements, acceptance, approach, and verification; PRs own evidence. Never mirror the same metadata or checklist in two places.
- Issue-governed work links to its real GitHub issue before implementation. Follow the repo's branch/release policy; resolve both the PR base and the remote default. Default-targeting PRs that fully resolve the issue use a closing keyword; legitimate non-default PRs use GitHub's explicit Development link. Read the link back either way; never retarget a PR just to link it.
- Before creating an issue, search related
Weaverseissues in all states (open and closed). Reuse a matching one, even if closed; if its scope changed, editing the issue body is an external write that needs approval for that issue and payload (read it first, preserve history/metadata, read back). Create new only when no genuine match exists. Reopen only when work actually resumes within authorization. - Small clear bugs/maintenance use the issue as the mini-spec. Substantive work uses one flat file
.weaverse/specs/YYYY-MM-DD-what-update.md(single hyphen after the date; no feature folder or per-specREADME.md; sections Outcome; Scope & contract; Acceptance; Approach; Verification). No newplan.md/work-logs.md/design.md/tasks.md/handoff.mdby default. - Search existing specs and linked issues first; update the closest canonical spec in place. The filename date is the creation date: never rename the file on update. Leave untouched legacy
.weaverse/specs/YYYY-MM-DD--title/folders as they are; when substantively editing one, consolidate that outcome into one flat spec file so only one maintained contract remains. - Requirements are concise, portable, professionally revised (no raw chat or private source paths); always redact secrets and private session material.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 16d ago Changed · +1 lines · +84 tokens per session 59d10e4e66d1
- 17d ago Changed · +1 lines · +24 tokens per session 856c09bbd933
- 24d ago Changed · +2 tokens per session e0c043548f0b
- 29d ago Changed · +62 tokens per session 0d4b28b603b3
- 1mo ago Changed · -1 lines · +63 tokens per session 0ffa48cf1a1b
- 2mo ago Changed · +3 lines · +211 tokens per session eaeed3a864b9
- 2mo ago First seen · 450 lines · 4,400 tokens per session scan A bc4d35c12ece
pilot AGENTS.md is an instructions file published in the GitHub repository Weaverse/pilot (387 stars, last pushed 3d ago), licensed MIT. It adds 4,846 tokens to every session, about $0.0194 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
pilot AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pilot AGENTS.mdWeaverse/pilot | Instructions file | 387 | 3d ago | MIT | A | 4,846 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |